© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56123
    Prev
    Next
    INDEX
    Explanations

    grep commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aren
    -0.08
    ارة
    -0.08
    eso
    -0.08
    éĻĦ带
    -0.07
    é«ĺè¿ľ
    -0.07
    ×ķ×ķ
    -0.07
     suerte
    -0.07
    amon
    -0.07
    Cover
    -0.07
    еÑĢе
    -0.07
    POSITIVE LOGITS
    umlu
    0.07
    ç½
    0.06
    Å«k
    0.06
     prop
    0.06
     relativo
    0.06
    çĽijçĿ£ç®¡çIJĨ
    0.06
    æ£ķæ¦Ī
    0.06
    .must
    0.06
    大ä¼ļåłĤ
    0.06
    ent
    0.06
    Activations Density 0.128%

    No Known Activations